BlogLLM Benchmark Scores as Published, Side by Side
KernelGen: Results as Published
Every result the catalog holds for KernelGen: 5 models from 1 developer, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area ML EngineeringMaintainer OpenAIIntroduced 2026Data version 2026103001, as of 2026-10-30
KernelGen 1P is an internal OpenAI evaluation of writing and optimizing compute kernels, part of the suite of real AI research tasks (debugging, kernel and training-recipe optimization, running experiments, improving another model) that OpenAI uses to measure how much a model speeds up its own research.
KernelGen 1P
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 45.34% | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 22.4% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 61.1% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 49.2% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 29.3% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.